发表机构
Concordia University（康考迪亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对医学图像分割难题，提出AdaKAN网络，它集成卷积操作与EffiKAN块，其含高效注意力机制和双分支AdaptKAN模块，采用U形架构与跳跃连接，在多医学成像数据集实验中分割精度达最优。
AI 中文摘要
医学图像分割是计算机辅助诊断中的一项基础任务，但由于解剖结构的复杂性和成像模态的变异性，它仍然具有挑战性。本文提出了AdaKAN，一种自适应柯尔莫哥洛夫 - 阿诺德网络（KAN），它将卷积操作与新颖的高效KAN（EffiKAN）块协同集成，该块由高效注意力机制和自适应KAN（AdaptKAN）模块组成。AdaptKAN模块具有双分支设计，一个分支采用具有伯恩斯坦多项式激活的KAN层进行全局平滑和稳定函数逼近，另一个分支通过投影操作和自适应缩放进行通道细化。AdaKAN采用U形架构，有效捕捉长距离依赖和细粒度局部特征，克服了传统卷积和基于Transformer的分割模型的局限性。跳跃连接用于在编码期间保留空间细节并在解码期间促进准确重建。在不同医学成像数据集上进行的大量实验表明，AdaKAN在分割精度方面达到了当前的最佳性能。
英文摘要
Medical image segmentation is a fundamental task in computer-aided diagnosis, yet it remains challenging due to the complexity of anatomical structures and the variability across imaging modalities. In this paper, we propose AdaKAN, an Adaptive Kolmogorov-Arnold Network (KAN) that synergistically integrates convolutional operations with a novel efficient KAN (EffiKAN) block, comprised of an efficient attention mechanism and an adaptive KAN (AdaptKAN) module. This module features a dual-branch design: one branch employs a KAN layer with Bernstein polynomial activations for globally smooth and stable function approximation, while the other branch performs channel-wise refinement through projection operations and adaptive scaling. AdaKAN adopts a U-shaped architecture that effectively captures both long-range dependencies and fine-grained local features, overcoming the limitations of conventional convolutional and Transformer-based segmentation models. Skip connections are employed to preserve spatial details during encoding and facilitate accurate reconstruction during decoding. Extensive experiments conducted on diverse medical imaging datasets demonstrate that AdaKAN achieves state-of-the-art performance in segmentation accuracy.
Journal refPattern Recognition Letters, 2026
